The questionnaire method is generally used for present dementia screening. However, this method requires time for 10 to 15 min with a doctor and a clinical psychologist, which puts a burden on hospitals and test subjects. The purpose of this study is to reduce the burden of users by constructing a system to distinguish patients with mild dementia and healthy persons from speech data. Before that this paper examines the effectiveness of speech features. MFCC has been confirmed to be effective in previous research, this paper extracted six kinds of other speech features that are likely to be correlated with symptoms of dementia. This paper got about 90% accuracy rate for a sentence of conversational speech in SVM and Random Forest. Moreover, this paper has calculated the importance of the features by using the SVM-RFE method. As a result, this showed that log-mel spectrum was more important than MFCC.
CITATION STYLE
Nishikawa, K., Hirakawa, R., Kawano, H., Nakashi, K., & Nakatoh, Y. (2021). Effective speech features for distinguishing mild dementia patients from healthy person. In Advances in Intelligent Systems and Computing (Vol. 1253 AISC, pp. 356–361). Springer. https://doi.org/10.1007/978-3-030-55307-4_54
Mendeley helps you to discover research relevant for your work.